Discrete Distributions in IronPython QuickStart Sample
Illustrates how to use the classes that represent discrete probability distributions in the Numerics.NET.Statistics.Distributions namespace in IronPython.
View this sample in: C# Visual Basic F#
```Python import numerics from System import Array from Extreme.Statistics import * from Extreme.Statistics.Distributions import * # Demonstrates how to use classes that implement # discrete probabililty distributions. # This QuickStart Sample demonstrates the capabilities of # the classes that implement discrete probability distributions. # These classes inherit from the DiscreteDistribution class. # # For an illustration of classes that implement discrete probability # distributions, see the ContinuousDistributions QuickStart Sample. # # We illustrate the properties and methods of discrete distribution # using a binomial distribution. The same properties and methods # apply to all other discrete distributions. # # Constructing distributions # # Many discrete probability distributions are related to Bernoulli trials, # events with a certain probability, p, of success. The number of trials # is often one of the distribution's parameters. # The binomial distribution has two constructors. Here, we create a # binomial distribution for 6 trials with a probability of success of 0.6: binomial = BinomialDistribution(6, 0.6) # The distribution's parameters are available through the # NumberOfTrials and ProbabilityOfSuccess properties: print "# of trials: {0}".format(binomial.NumberOfTrials) print "Prob. of success: {0:.5f}".format(binomial.ProbabilityOfSuccess) # # Basic statistics # # The Mean property returns the mean of the distribution: print "Mean: {0:.5f}".format(binomial.Mean) # The Variance and StandardDeviation are also available: print "Variance: {0:.5f}".format(binomial.Variance) print "Standard deviation: {0:.5f}".format(binomial.StandardDeviation) # As are the skewness: print "Skewness: {0:.5f}".format(binomial.Skewness) # The Kurtosis property returns the kurtosis supplement. # The Kurtosis property for the normal distribution returns zero. print "Kurtosis: {0:.5f}".format(binomial.Kurtosis) print # # Distribution functions # # The (cumulative) distribution function (CDF) is implemented by the # DistributionFunction method: print "CDF(4) = {0:.5f}".format(binomial.DistributionFunction(4)) # The probability density function (PDF) is available as the # Probability method: print "PDF(4) = {0:.5f}".format(binomial.Probability(4)) # The Probability method has an overload that returns the probability # that a variate lies between two values: print "Probability(3, 5) = {0:.5f}".format(binomial.Probability(3, 5)) print # # Random variates # # The Sample method returns a single random variate # using the specified random number generator: rng = Random.MersenneTwister() x = binomial.Sample(rng) # The Sample method fills an array or vector with # random variates. It has several overloads: xArray = Array.CreateInstance(int, 100) # 1. Fill all values: binomial.Sample(rng, xArray) # 2. Fill only a range (start index and length are supplied) binomial.Sample(rng, xArray, 20, 50) # The GetExpectedHistogram method returns a Histogram that contains the # expected number of samples in each bin: h = binomial.GetExpectedHistogram(100) print "Expected distribution of 100 samples:" for bin in h.Bins: print "{0} success(es) -> {1}".format(bin.LowerBound, bin.Value) ```